In this paper we present an approach for creating complete shape representations from a single depth image for robot grasping. We introduce algorithms for completing partial point clouds based on the analysis of symmetry and extrusion patterns in observed shapes. Identified patterns are used to generate a complete mesh of the object, which is, in turn, used for grasp planning. The approach allows robots to predict the shape of objects and include invisible regions into the grasp planning step. We show that the identification of shape patterns, such as extrusions, can be used for fast generation and optimization of grasps. Finally, we present experiments performed with our humanoid robot executing pick-up tasks based on single depth images and discuss the applications and shortcomings of our approach.
With the advent of affordable RGBD sensors such as the Kinect, the collection of depth and appearance information from a scene has become effortless. However, neither the correct noise model for these sensors, nor a principled methodology for extracting planar segmentations has been developed yet. In this work, we advance the state of art with the following contributions: we correctly model the Kinect sensor data by observing that the data has inherent noise only over the measured disparity values, we formulate plane fitting as a linear least-squares problem that allow us to quickly merge different segments, and we apply an advanced Markov Chain Monte Carlo (MCMC) method, generalized Swendsen-Wang sampling, to efficiently search the space of planar segmentations. We evaluate our plane fitting and surface reconstruction algorithms with simulated and real-world data.
Flow forming is an incremental metal-forming technique used for manufacturing thin-walled seamless tubes where a hollow metal material flows axially along the mandrel by a rotating mandrel and multiple cylinders. Flow formed materials are frequently used in the aviation and defence industry and it is crucial to examine the influence of the process on the material in terms of ductile fracture. However, the process requires in-depth failure analysis considering different process parameters and materials. The current study is concerned with investigating the ductile fracture behavior during flow forming process which includes complex stress states in terms of stress triaxiality and Lode parameter. Ductile fracture is simulated through the modified Mohr-Coulomb model. A user material subroutine (VUMAT) has been developed to implement the plasticity behavior and the damage accumulation rule. The model is validated through finite element (FE) simulations performed in Abaqus/Explicit and using the experimental data in Granum et al. (2021). The validated framework is applied to a finite element model of flow forming process with single and three rollers. The incremental forming with three rollers significantly reduces the damage accumulation. The initial results show a highly damaged region outer and inner surfaces of the workpiece after 40% thickness reduction ratio, and the forming limit is predicted as about 40-45%. The modeling framework is planned to be applied using various process parameter for different materials.
When the sensor is placed before the end-effector, the sensor measures not only the external forces and torques acting on the end-effector but also those due to the weight and motion of the end-effector itself. We need to compensate for this effect of the end-effector to attain accurate estimation of the external force on the end-effector. A secondary problem is the drift in the sensor values, that is the sensor values, in time, slowly change to a wrong value due to fabrication imperfections, heat and etc. A common approach is to compute an offset between the measurements and the true state of the sensor. For instance, if the gripper is isolated and stationary, then the readings should reflect only its weight. In such a situation, we can compute a new offset that we will keep decreasing from the future readings to estimate the true value. After a while, as the drift changes the readings again, we will recompute this offset in an appropriate scenario.
The purpose of this document is to establish a technical framework to control Krang in its stable balancing state. We will first discuss related work in inverted pendulum-like systems to get acquianted with the literature. Next, we will present a simple inverted pendulum model, analyze the dynamics and simulate it. We will evaluate the effect of different control gains in state feedback control and analyze the effect of noise in output feedback control. Lastly, we will study the effect of modeling errors in mass measurements.
The RoboCup robot soccer Small Size League has been running since 1997 with many teams successfully competing and very effectively playing the games. Teams of five robots, with a combined autonomous centralized perception and control, and distributed actuation, move at high speeds in the field space, actuating a golf ball by passing and shooting it to aim at scoring goals. Most teams run their own pre-defined team strategies, unknown to the other teams, with flexible game-state dependent assignment of robot roles and positioning. However, in this fast-paced noisy real robot league, recognizing the opponent team strategies and accordingly adapting one's own play has proven to be a considerable challenge. In this work, we analyze logged data of real games gathered by the CMDragons team, and contribute several results in learning and responding to opponent strategies. We define episodes as segments of interest in the logged data, and introduce a representation that captures the spatial and temporal data of the multi-robot system as instances of geometrical trajectory curves. We then learn a model of the team strategies through a variant of agglomerative hierarchical clustering. Using the learned cluster model, we are able to classify a team behavior incrementally as it occurs. Finally, we define an algorithm that autonomously generates counter tactics, in a simulation based on the real logs, showing that it can recognize and respond to opponent strategies.
Robots are inherently limited by constraints on their motor power, battery life, and structural rigidity. Using simple machines and exploiting their mechanical advantage can significantly increase the breadth of a robot's capabilities. In this work, we present an autonomous planner which allows a robot to determine how arbitrary rigid objects in its environment can be utilized in machine designs to overcome physical challenges. First, the designed structure must be sufficient to achieve a task given the input force and torque that can be applied by the robot. Second, the structure must be accessible to the robot given its kinematics and geometry so that it can actually be used to perform the task. The output of our algorithm is the configuration of the design components, the pose of the robot to make contact with the design, and the motor torques needed to actuate it. We demonstrate results with the robot Golem Krang, using levers as simple machines, to overturn 100 kg load and to push 240 kg wheeled obstacle.
Severe plastic deformation (SPD) can fabricate high-strength materials by forming an ultrafine grained (UFG) microstructure. Low elongation to failure of UFG materials in tensile tests, which has often been regarded as a measure of ductility of materials, has been attributed to low strain hardening of UFG structures where dislocation slip and its accumulation is very limited. In the present work, it is shown that the compressive extensibility of UFG materials can be comparable or potentially superior to that of annealed materials by using a parallel round-bar compression (PRBC) test which was designed for imposing an appropriate stress state preferable for high ductility using the shear mode. The high compressive extensibility of UFG materials can be a result of high accommodation of local strain incompatibility at non-equilibrium grain boundaries and a grain boundary-mediated deformation mechanism, which result in high damage tolerance against void formation and growth. Low strain rate sensitivity indicated that the superplastic viscous nature of deformation is not involved in the high compressive ductility of UFG materials using SPD.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)